iBreakDown
Model Agnostic Instance Level Variable Attributions
Model agnostic tool for decomposition of predictions from black boxes. Supports additive attributions and attributions with interactions. The Break Down Table shows contributions of every variable to a final prediction. The Break Down Plot presents variable contributions in a concise graphical way. This package works for classification and regression models. It is an extension of the 'breakDown' package (Staniak and Biecek 2018) doi:10.32614/RJ-2018-072, with new and faster strategies for orderings. It supports interactions in explanations and has interactive visuals (implemented with 'D3.js' library). The methodology behind is described in the 'iBreakDown' article (Gosiewska and Biecek 2019) doi:10.48550/arXiv.1903.11420. This package is a part of the 'DrWhy.AI' universe (Biecek 2018) doi:10.48550/arXiv.1806.08915.
- Version2.1.2
- R versionunknown
- LicenseGPL-3
- Needs compilation?No
- iBreakDown citation info
- Last release12/01/2023
Documentation
Team
Przemyslaw Biecek
Alicja Gosiewska
Show author detailsRolesAuthorHubert Baniecki
Show author detailsRolesAuthorAdam Izdebski
Show author detailsRolesAuthorDariusz Komosinski
Show author detailsRolesContributor
Insights
Last 30 days
This package has been downloaded 4,232 times in the last 30 days. Now we’re talking! This work is officially 'heard of in academic circles', just like those wild research papers on synthetic bananas. The following heatmap shows the distribution of downloads per day. Yesterday, it was downloaded 120 times.
Last 365 days
This package has been downloaded 57,838 times in the last 365 days. The kind of number that gets mentioned in a keynote speech. Well done! The day with the most downloads was Jan 21, 2024 with 1,336 downloads.
The following line graph shows the downloads per day. You can hover over the graph to see the exact number of downloads per day.
Data provided by CRAN
Binaries
Dependencies
- Imports1 package
- Suggests11 packages
- Reverse Imports4 packages